Links

To collect my links to keep I'll post them here. If someone got other sources of interest I'll appreciate any comments!!

Interesting Videos:

• interesting methods on scalable simulations...

 

• other interesting viedos: http://www.youtube.com/user/thebrainmission/

web sites:

• http://www.gluck.edu/   very active and interesting researcher...to review books and articles...

Papers to be reviewed:
http://home.earthlink.net/~perlewitz/papers.html

Basic concepts

Having explained the rough idea what and why I want to investiage it’s time to jump in the topic.

I said I don’t want to explain perceptrons and so on. Nevertheless I’d like to make you familiar with my visualalisation of neurons and there connections:

Of course the dentrits connect via synapses (e.g. modeling weights). We have a threshold and an activation function. So this is a very simple view on the structure, but all considered that’s usually involved.

Now I want to show what I think should be the starting point based on the knowledge I have.

So what we have here is looking like a normal feed forward neural network (ff-NN). But I would like to take feedback connections and lateral connections into account as well. Also, I deliberately missed out an output layer. That is because this network shall not work like a conventional ff-NN in terms of training. Furthermore we have a timing related propagation so the network is able to “remember” sequences, which is vital for expectations the network will produce from its stimuli. The first approach will include a simulation toolset in which you can model NN. I won’t focus on user-interfaces. It will be more like a framework. I plan to focus on scalability and want a 3D-simulation view to visualize the propagation loop. I hope this sounds exciting. More’s coming soon.

Thank you for reading.

OK, what's this about?

Hi,

My name is Wolfram Wagner and I work as a software engineer and technical consultant in Dresden Germany at the moment. My passion is finding solutions for custom software solutions in terms of neat architectures, design and implementation. Furthermore I am very interested in music, I play guitar, sing and think about intelligence, sociology and artificial intelligence…

So, what do I want to cover with this blog and why? What can we accomplish?

When I first heard of "soft computing" and all that stuff in course models at University I was fascinated by how simple the basic pattern of the brain seem to be. We saw pictures of neurons like the one you can see here:

source: http://users.tamuk.edu/kfjab02/Biology/AnimalPhysiology/B3408%20Systems/systems%20images/neuron.png.jpg

…and how easy it is to extract simple models from it that can actually be simulated on common computers. Enough with this, as all of you know what perceptrons and self-organising maps are (For all who don’t, please have a look at google and Wikipedia. There’s plenty of good and easy to understand stuff on the net….so I don’t want to repeat this here. BUT: Feel encouraged to read some stuff. It’s easier to understand than you’d think!)

My generally idea of things in the world is that all has simple concepts that need to be found and used to solve complicated looking things. That's why I'd like to share my thoughts thought this blog to let you know. And give you the chance to correct me and give impulses. So please feel free to drop comments! (German or English)

Why? I think it is possible to reproduce real intelligence. When we achieve this we might be able to better understand what intelligence really is. Or can we reproduce only if we know what it is? Hopefully we find out. But: I don’t want to argue on this…

We? I hope people like to follow and present their ideas and feelings about this topic. Isn’t it time to start thinking together? What could a single neuron achieve on its own? You see what I mean.

Thanks for reading. I appreciate your time.

Wolfram

Ready. Steady, Go!

Ein Anfang ist gemacht. Die Reise ist begonnen. Wir schreiben das Jahr 2011 und ich hoffe wir können dem Gehirn auf die Spur kommen.
---
The first step is taken. The journey started. It's 2011 and I hope we can get a sniff of the brain.